keras TripletSemiHardLoss请求形状32 [[{{node TripletSemiHardLoss/PartitionedCall/Reshape}}]] [Op：__inference_train_function_1666]

我目前正在研究一个用例，我想使用TripletSemiHardLoss来获得相似度的排名。基本上，我有一个训练文件，其中有分类变量，每组变量都有一个对应的类别（标签），它应该与之相关联。为了实现这一点，我实现了以下代码：
导入数据，进行one-hot编码，在锚、正、负集合中分离，建立模型并训练：

def learn_ranking_loss(settings):
    training_data, label_columns, label_dict, features_dict, losses, loss_weights = data_handling.training_data_labeling(
        ['Diagnosis'], settings["CONFIGURATION_FILE_PATH"], binary_features=settings["BINARY_FEATURES"],
        ignore=['Runtime', 'Consistency check'])
    train_x, test_x, train_labels, test_labels, input_neuron_list, output_neuron_list = data_preprocessing.data_preprocessing_learning(
        training_data, label_columns)

    training_data = tf.data.Dataset.zip(
        (tf.data.Dataset.from_tensor_slices(train_x[:(round(len(train_x) / 3))]),
         tf.data.Dataset.from_tensor_slices(
             train_x[(round(len(train_x) / 3)):(round(len(train_x) / 3) * 2)]),
         tf.data.Dataset.from_tensor_slices(
             train_x[(round(len(train_x) / 3) * 2):])))
    train_labels = tf.data.Dataset.zip(
        (tf.data.Dataset.from_tensor_slices(train_labels[0][:(round(len(train_labels[0]) / 3))]),
         tf.data.Dataset.from_tensor_slices(
             train_labels[0][(round(len(train_labels[0]) / 3)):(round(len(train_labels[0]) / 3) * 2)]),
         tf.data.Dataset.from_tensor_slices(
             train_labels[0][(round(len(train_labels[0]) / 3) * 2):])))

    dataset = tf.data.Dataset.zip((training_data, train_labels)).batch(32)

    emb_mod, model = get_siamese_model([287, ])

    # Compile the model
    model.compile(
        optimizer=tf.keras.optimizers.Adam(0.001),
        loss=tfa.losses.TripletSemiHardLoss())

    # Train the network
    history = model.fit(
        dataset,
        epochs=1)
    return

基于输入的独热编码创建的Tensor是[287，]，标签的形状是[52，]。
模型的创建如下：

def create_model(input_shape):
    inp = tf.keras.layers.Input(shape=input_shape)
    x = tf.keras.layers.Dense(287, activation='relu')(inp)
    x = tf.keras.layers.Dense(287, activation='relu')(x)
    x = tf.keras.layers.Dense(52, activation=None)(x)
    # x = tf.keras.layers.Lambda(lambda y: tf.math.l2_normalize(x, axis=1))(x)
    model = tf.keras.Model(inp, x)
    return model

def get_siamese_model(input_shape):

    # Define the tensors for the triplet of input images
    anchor_input = tf.keras.layers.Input(input_shape, name="anchor_input")
    positive_input = tf.keras.layers.Input(input_shape, name="positive_input")
    negative_input = tf.keras.layers.Input(input_shape, name="negative_input")

    # Convolutional Neural Network (same from earlier)
    embedding_model = create_model(input_shape)

    # Generate the embedding outputs
    encoded_anchor = embedding_model(anchor_input)
    encoded_positive = embedding_model(positive_input)
    encoded_negative = embedding_model(negative_input)

    inputs = [anchor_input, positive_input, negative_input]
    outputs = [encoded_anchor, encoded_positive, encoded_negative]
    # x = tf.keras.layers.Lambda(lambda x: tf.math.l2_normalize(outputs, axis=1))(outputs)

    # Connect the inputs with the outputs
    siamese_triplet = tf.keras.Model(inputs=inputs, outputs=outputs)

    # return the model
    return embedding_model, siamese_triplet

运行代码时，返回以下错误消息：

Traceback (most recent call last):
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\ranking_loss.py", line 94, in <module>
    learn_ranking_loss(settings_dict)
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\ranking_loss.py", line 74, in learn_ranking_loss
    history = model.fit(
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\keras\engine\training.py", line 1189, in fit
    tmp_logs = self.train_function(iterator)
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\def_function.py", line 885, in __call__
    result = self._call(*args, **kwds)
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\def_function.py", line 950, in _call
    return self._stateless_fn(*args, **kwds)
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\function.py", line 3039, in __call__
    return graph_function._call_flat(
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\function.py", line 1963, in _call_flat
    return self._build_call_outputs(self._inference_function.call(
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\function.py", line 591, in call
    outputs = execute.execute(
  File "C:\Users\mathi\Documents\Studium\Promotion\ConLearn\Python interpreter\lib\site-packages\tensorflow\python\eager\execute.py", line 59, in quick_execute
    tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Input to reshape is a tensor with 1664 values, but the requested shape has 32
     [[{{node TripletSemiHardLoss/PartitionedCall/Reshape}}]] [Op:__inference_train_function_1666]

Function call stack:
train_function

Process finished with exit code 1

在做了一些研究后，我确信这个问题是由我的层的形状引起的，但我无法找出需要改变的地方。我还观察到1664除以32正好是52，所以输出形状。此外，如果我改变我的层的形状，无论发生什么同样的问题。
任何帮助都将非常感激。非常感谢！
最好的问候，马蒂亚斯

我已经发现并解决了这个问题。
问题是tensorflow TripletSemiHardLoss期望标签作为分类输入（每个训练项的一系列简单的分类值）。错误是对标签进行one-hot编码，就像你通常对交叉熵损失函数所做的那样。
请在下面找到固定的代码。还请注意，我在训练期间从离线选择锚，positive和negative改为在线选择相同的锚点，因为它是由tensorflow实现TripletSemiHardLoss支持的：

def create_model(input_shape):
inp = tf.keras.layers.Input(shape=input_shape)
x = tf.keras.layers.Dense(280, activation='relu')(inp)
y = tf.keras.layers.Dense(280, activation='relu')(x)
z = tf.keras.layers.Dense(52, activation=None)(y)
# l2_normalization = tf.keras.layers.Lambda(lambda y: tf.math.l2_normalize(y, axis=1))(z)

model = tf.keras.Model(inp, z)
return model

def learn_ranking_loss(settings):
one_hot = OneHotEncoder()

# get data
# build training data set
training_data, label_columns, label_dict, features_dict, losses, loss_weights = data_handling.training_data_labeling(
    ['Diagnosis'], settings["CONFIGURATION_FILE_PATH"], binary_features=settings["BINARY_FEATURES"],
    ignore=['Runtime', 'Consistency check'])
train_x = np.array(training_data)
train_x = one_hot.fit_transform(train_x).toarray()
train_y = label_columns[0].to_numpy()
train_dataset = tf.data.Dataset.from_tensor_slices((train_x, train_y))
train_dataset = train_dataset.batch(128)

# build test data set
validation_data, label_columns, label_dict, losses, loss_weights = data_handling.data_labeling(
    ['Diagnosis'], settings["VALIDATION_FILE_PATH"], binary_features=settings["BINARY_FEATURES"],
    ignore=['Runtime', 'Consistency check'])
test_x = np.array(validation_data)
test_x = one_hot.fit_transform(test_x).toarray()
test_y = label_columns[0].to_numpy()
test_dataset = tf.data.Dataset.from_tensor_slices((test_x, test_y))
test_dataset = test_dataset.batch(128)

if not data_handling.data_consistency_triplet_loss(training_data, validation_data):
    return

# create model
model = create_model([280, ])
# emb_mod, model = get_siamese_model([280, ])

# train model
epochs = 3
lr = 0.001
optimizer = tf.optimizers.Adam(learning_rate=lr)

model.compile(optimizer=optimizer, loss=tfa.losses.TripletSemiHardLoss())  # , metrics=["accuracy"])
model.summary()

history = model.fit(train_dataset, epochs=epochs) 
return

希望这对将来遇到同样问题的人有所帮助。
最好的问候，马蒂亚斯

keras TripletSemiHardLoss请求形状32 [[{{node TripletSemiHardLoss/PartitionedCall/Reshape}}]] [Op：__inference_train_function_1666]

1条答案

相关问题

热门标签

最新问答